© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89786
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to influence or impact in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orage
    -0.07
     hopes
    -0.06
    ãĥĩãĥ«
    -0.06
    fad
    -0.06
    ÙĪÙĬØ©
    -0.06
     ENTITY
    -0.06
     Expires
    -0.06
    _DEVICES
    -0.06
    uddle
    -0.06
    wear
    -0.06
    POSITIVE LOGITS
     presence
    0.08
    meli
    0.07
    alone
    0.07
    ìłĢ
    0.07
    itone
    0.07
     meiden
    0.07
     combination
    0.07
     mere
    0.07
    presence
    0.07
    ÃŃky
    0.06
    Activations Density 0.025%

    No Known Activations